Group-wise Deep Co-saliency Detection

TL;DR

This paper introduces an end-to-end deep learning method for co-saliency detection that captures group interactions and learns group-wise features to improve the discovery of common salient objects across image groups.

Contribution

It presents a novel group-wise deep co-saliency detection framework that jointly learns group and individual features in an end-to-end manner, enhancing detection accuracy.

Findings

Outperforms state-of-the-art methods in co-saliency detection

Effectively models group interactions for better object discovery

Achieves robust results across various datasets

Abstract

In this paper, we propose an end-to-end group-wise deep co-saliency detection approach to address the co-salient object discovery problem based on the fully convolutional network (FCN) with group input and group output. The proposed approach captures the group-wise interaction information for group images by learning a semantics-aware image representation based on a convolutional neural network, which adaptively learns the group-wise features for co-saliency detection. Furthermore, the proposed approach discovers the collaborative and interactive relationships between group-wise feature representation and single-image individual feature representation, and model this in a collaborative learning framework. Finally, we set up a unified end-to-end deep learning scheme to jointly optimize the process of group-wise feature representation learning and the collaborative learning, leading to more reliable and robust co-saliency detection results. Experimental results demonstrate the effectiveness of our approach in comparison with the state-of-the-art approaches.